Triple

T13876594
Position Surface form Disambiguated ID Type / Status
Subject Karamoja region E333598 entity
Predicate contains P35 FINISHED
Object Kaabong District E1002212 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kaabong District | Statement: [Karamoja region, contains, Kaabong District]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaabong District
Context triple: [Karamoja region, contains, Kaabong District]
  • A. Kaabong District chosen
    Kaabong District is an administrative district in northeastern Uganda known for its remote, semi-arid landscape and predominantly pastoralist communities.
  • B. Butambala District
    Butambala District is a rural administrative district in central Uganda known for its predominantly agricultural economy and small trading centers.
  • C. Monywa District
    Monywa District is an administrative district in Myanmar’s Sagaing Region, centered around the city of Monywa and known for its agricultural economy and regional trade.
  • D. Tembuku District
    Tembuku District is an administrative district in the regency of Bangli on the island of Bali, Indonesia.
  • E. Magu District
    Magu District is an administrative district in northern Tanzania, located within the Mwanza Region along the southern shores of Lake Victoria.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de0be556708190bbcf0b3583f677e3 completed April 14, 2026, 9:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d72a17c8190b63f9f441731917d completed May 8, 2026, 4:58 a.m.
Created at: April 9, 2026, 10:15 p.m.